mamba-130m / config.json
Wauplin's picture
Wauplin HF staff
Push model using huggingface_hub.
6d4b46a verified
raw
history blame
312 Bytes
{
"bias": false,
"conv_bias": true,
"d_conv": 4,
"d_model": 768,
"d_state": 16,
"device": null,
"dt_init": "random",
"dt_init_floor": 0.0001,
"dt_max": 0.1,
"dt_min": 0.001,
"dt_rank": "auto",
"dt_scale": 1.0,
"dtype": null,
"expand": 2,
"layer_idx": null,
"use_fast_path": true
}